상세정보
학술지
Multi-View Integrative Attention-Based Deep Representation Learning for Irregular Clinical Time-Series Data
- 저자
- 이유림, 전지은, 최재훈, 석흥일
- 발행일
- 202208
- 출처
- IEEE Journal of Biomedical and Health Informatics, v.26 no.8, pp.4270-4280
- ISSN
- 2168-2208
- 출판사
- IEEE
- 협약과제
- 22HR6200, 최적 치료 협진 서비스를 위한 다기관 분산지능 강화 페더레이션 기술 개발, 최재훈
- 초록
- Electronic health record (EHR) data are sparse and irregular as they are recorded at irregular time intervals, and different clinical variables are measured at each observation point. In this work, to handle irregular multivariate time-series data, we consider the human knowledge of the aspects to be measured and time to measure them in different situations, known as multi-view features, which are indirectly represented in the data. We propose a scheme to realize multi-view features integration learning via a self-attention mechanism. Specifically, we devise a novel multi-integration attention module (MIAM) to extract complex information that is inherent in irregular time-series data. We explicitly learn the relationships among the observed values, missing indicators, and time interval between the consecutive observations in a simultaneous manner. In addition, we build an attention-based decoder as a missing value imputer that helps empower the representation learning of the interrelations among multi-view observations for the prediction task this decoder operates only in the training phase so that the final model is implemented in an imputation-free manner. We validated the effectiveness of our method over the public MIMIC-III and PhysioNet challenge 2012 datasets by comparing with and outperforming the state-of-the-art methods in three downstream tasks i.e., prediction of the in-hospital mortality, prediction of the length of stay, and phenotyping. Moreover, we conduct a layer-wise relevance propagation (LRP) analysis based on case studies to highlight the explainability of the trained model.
- KSP 제안 키워드
- Attention mechanism, Case studies, Clinical variables, Complex information, Deep representation learning, Human knowledge, In-hospital mortality, Length of Stay(LOS), Missing values, Multi-view features, Multivariate time series